Onboard Optimization and Learning: A Survey
It addresses the problem of enabling real-time, low-latency, and privacy-preserving AI applications on edge devices for fields like IoT and autonomous systems, but it is incremental as a survey rather than a novel method.
This survey tackles the challenges of implementing AI on resource-constrained edge devices by exploring methodologies for optimizing model efficiency, accelerating inference, and supporting collaborative learning, providing insights into the current state of onboard learning to enable robust and secure AI deployment.
Onboard learning is a transformative approach in edge AI, enabling real-time data processing, decision-making, and adaptive model training directly on resource-constrained devices without relying on centralized servers. This paradigm is crucial for applications demanding low latency, enhanced privacy, and energy efficiency. However, onboard learning faces challenges such as limited computational resources, high inference costs, and security vulnerabilities. This survey explores a comprehensive range of methodologies that address these challenges, focusing on techniques that optimize model efficiency, accelerate inference, and support collaborative learning across distributed devices. Approaches for reducing model complexity, improving inference speed, and ensuring privacy-preserving computation are examined alongside emerging strategies that enhance scalability and adaptability in dynamic environments. By bridging advancements in hardware-software co-design, model compression, and decentralized learning, this survey provides insights into the current state of onboard learning to enable robust, efficient, and secure AI deployment at the edge.